tighten-prose

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious scripts, hardcoded credentials, or obfuscated commands were detected.
  • [EXTERNAL_DOWNLOADS]: The skill fetches current AI vocabulary lists from the Wikipedia API. This is a well-known service used to provide dynamic style guidelines.
  • [PROMPT_INJECTION]: The skill identifies and processes external data from Wikipedia and user-provided text. Ingestion points: Wikipedia API and user-supplied prose. Boundary markers: Not explicitly defined. Capability inventory: Restricted to text analysis and rewriting; no file-system or network-writing capabilities are present. Sanitization: The agent is instructed to extract specific word lists from the fetched content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 06:25 AM
Security Audit — agent-trust-hub — tighten-prose